{"id":"https://openalex.org/W4413925099","doi":"https://doi.org/10.1109/icra55743.2025.11128752","title":"Hierarchical Visual Policy Learning for Long-Horizon Robot Manipulation in Densely Cluttered Scenes","display_name":"Hierarchical Visual Policy Learning for Long-Horizon Robot Manipulation in Densely Cluttered Scenes","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925099","doi":"https://doi.org/10.1109/icra55743.2025.11128752"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091130042","display_name":"Hecheng Wang","orcid":"https://orcid.org/0000-0001-9873-1626"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hecheng Wang","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009450745","display_name":"Lizhe Qi","orcid":"https://orcid.org/0000-0002-4348-1559"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhe Qi","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597575","display_name":"Ziheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziheng Wang","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079239174","display_name":"Jiankun Ren","orcid":"https://orcid.org/0000-0001-6544-2246"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiankun Ren","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736642","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-7269-2742"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005919686","display_name":"Yunquan Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunquan Sun","raw_affiliation_strings":["Fudan University,Academy for Engineering & Technology,Shanghai,China"],"affiliations":[{"raw_affiliation_string":"Fudan University,Academy for Engineering & Technology,Shanghai,China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5091130042"],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":1.319,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85130343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1149","last_page":"1155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6294000148773193,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6294000148773193,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.6169999837875366,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.5720999836921692,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.6683194637298584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6673594117164612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.660161018371582},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6398586630821228},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5788464546203613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.090004563331604}],"concepts":[{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.6683194637298584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6673594117164612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.660161018371582},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6398586630821228},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5788464546203613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.090004563331604},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2109910161","https://openalex.org/W2113122939","https://openalex.org/W2962793652","https://openalex.org/W2975504670","https://openalex.org/W3004047800","https://openalex.org/W3034988830","https://openalex.org/W3089482831","https://openalex.org/W3089825434","https://openalex.org/W3089883116","https://openalex.org/W3127940962","https://openalex.org/W3130885760","https://openalex.org/W3134939669","https://openalex.org/W3176770340","https://openalex.org/W3183217451","https://openalex.org/W3200958309","https://openalex.org/W3204657926","https://openalex.org/W3207181464","https://openalex.org/W3210327237","https://openalex.org/W3216082637","https://openalex.org/W4207021923","https://openalex.org/W4221152092","https://openalex.org/W4249742433","https://openalex.org/W4283787240","https://openalex.org/W4285102264","https://openalex.org/W4285102485","https://openalex.org/W4285164516","https://openalex.org/W4285285192","https://openalex.org/W4313000235","https://openalex.org/W4318464334","https://openalex.org/W4323527523","https://openalex.org/W4360897660","https://openalex.org/W4383109305","https://openalex.org/W4389667706"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,80,96],"focus":[4],"on":[5,32],"addressing":[6],"the":[7,69,88,105,108,119,125,157],"long-horizon":[8],"packing":[9],"tasks":[10,16,145],"in":[11,123,136,143,147,164],"densely":[12],"cluttered":[13],"scenes.":[14],"Such":[15],"require":[17],"policies":[18],"to":[19,54,86,103,117],"effectively":[20],"manage":[21],"severe":[22],"occlusions":[23],"among":[24],"objects":[25],"and":[26,51,56,64,72,91,111,141,149,162],"continually":[27],"produce":[28],"precise":[29],"actions":[30],"based":[31],"visual":[33],"observations.":[34],"We":[35,66,128],"propose":[36,97],"a":[37,48,98,112],"vision-based":[38],"Hierarchical":[39],"policy":[40,50,90],"for":[41,107],"Cluttered-scene":[42],"Long-horizon":[43],"Manipulation":[44],"(HCLM).":[45],"It":[46],"employs":[47],"high-level":[49,89,126],"three":[52,58],"options":[53,74],"select":[55],"instantiate":[57],"parameterized":[59],"action":[60],"primitives:":[61],"push,":[62],"pick,":[63],"place.":[65],"first":[67],"train":[68,87],"two-stream":[70],"pick":[71],"place":[73],"by":[75],"behavior":[76],"cloning":[77],"(BC).":[78],"Subsequently,":[79],"use":[81],"hierarchical":[82],"reinforcement":[83],"learning":[84],"(HRL)":[85],"push":[92,109],"option.":[93],"During":[94],"HRL,":[95],"Spatially":[99],"Extended":[100],"Q-update":[101],"(SEQ)":[102],"augment":[104],"updates":[106],"option":[110],"Two-Stage":[113],"Update":[114],"Scheme":[115],"(TSUS)":[116],"alleviate":[118],"non-stationary":[120],"transition":[121],"problem":[122],"updating":[124],"policy.":[127],"demonstrate":[129],"that":[130],"HCLM":[131],"significantly":[132],"outperforms":[133],"baseline":[134],"methods":[135],"terms":[137],"of":[138,160],"success":[139],"rate":[140],"efficiency":[142],"diverse":[144],"both":[146],"simulation":[148],"real":[150],"world.":[151],"The":[152],"ablation":[153],"studies":[154],"also":[155],"validate":[156],"key":[158],"roles":[159],"SEQ":[161],"TSUS":[163],"HRL.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}